init
Warn
Audited by Snyk on Feb 26, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.90). The skill's SKILL.md explicitly directs the agent to use WebFetch on a user-provided website (homepage, about, services pages and optional LinkedIn) and ingest those public, untrusted pages to populate CLAUDE.md and drive subsequent agent behavior, which could allow indirect prompt injection.
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (high risk: 0.80). The skill uses WebFetch at runtime to fetch the user-provided website URL (e.g., https://example.com) and injects that remote site content into prompts to control the agent's generated company profile, so the external URL directly influences agent instructions and is required for the setup flow.
Audit Metadata